{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NPXG26NONTZMMBTILRZ3EY6KWU","short_pith_number":"pith:NPXG26NO","schema_version":"1.0","canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","source":{"kind":"arxiv","id":"1901.08277","version":3},"attestation_state":"computed","paper":{"title":"Federated Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hankz Hankui Zhuo, Qiang Yang, Qian Xu, Wenfeng Feng, Yufeng Lin","submitted_at":"2019-01-24T08:25:29Z","abstract_excerpt":"In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Despite the success of previous transfer learning approaches in deep reinforcement learning, directly transferring data or models from an agent to another agent is often not allowed due to the privacy of data and/or models in many privacy-aware applications. In this paper, we propose a novel deep reinforcement learning framework to federatively build models of high-quality for agents with consideration of their privacies, namely Federated "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1901.08277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T08:25:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"baa2ca1e5118de87056e5ffae21af3e7079a173583dbbc0356cd0f6c1f723730","abstract_canon_sha256":"e9ad04da246cd2bd9ce8a12c7074f479d74e10440b951b03d1839a9029254f90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:10.069805Z","signature_b64":"zX5wbMXsg/7dQ8G0Im2yKCfj7g9NWXHxVIStX9UG51DN8ybpV+Eytmy3FmaaDwxEIOXgNGpo41RJMpI40NOxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bee6d79ae6cf2c606685c73b263cab5017d2ae45c6b808c3c488975f3d3e5af","last_reissued_at":"2026-07-05T00:39:10.069373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:10.069373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hankz Hankui Zhuo, Qiang Yang, Qian Xu, Wenfeng Feng, Yufeng Lin","submitted_at":"2019-01-24T08:25:29Z","abstract_excerpt":"In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Despite the success of previous transfer learning approaches in deep reinforcement learning, directly transferring data or models from an agent to another agent is often not allowed due to the privacy of data and/or models in many privacy-aware applications. In this paper, we propose a novel deep reinforcement learning framework to federatively build models of high-quality for agents with consideration of their privacies, namely Federated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08277","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1901.08277/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1901.08277","created_at":"2026-07-05T00:39:10.069444+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08277v3","created_at":"2026-07-05T00:39:10.069444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08277","created_at":"2026-07-05T00:39:10.069444+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPXG26NONTZM","created_at":"2026-07-05T00:39:10.069444+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPXG26NONTZMMBTI","created_at":"2026-07-05T00:39:10.069444+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPXG26NO","created_at":"2026-07-05T00:39:10.069444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29002","citing_title":"FedQHD: Closed-Form Function-Space Federated Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20031","citing_title":"Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08378","citing_title":"Reinforcement Learning for Scalable and Trustworthy Intelligent Systems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20031","citing_title":"Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU","json":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU.json","graph_json":"https://pith.science/api/pith-number/NPXG26NONTZMMBTILRZ3EY6KWU/graph.json","events_json":"https://pith.science/api/pith-number/NPXG26NONTZMMBTILRZ3EY6KWU/events.json","paper":"https://pith.science/paper/NPXG26NO"},"agent_actions":{"view_html":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU","download_json":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU.json","view_paper":"https://pith.science/paper/NPXG26NO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08277&json=true","fetch_graph":"https://pith.science/api/pith-number/NPXG26NONTZMMBTILRZ3EY6KWU/graph.json","fetch_events":"https://pith.science/api/pith-number/NPXG26NONTZMMBTILRZ3EY6KWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/action/storage_attestation","attest_author":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/action/author_attestation","sign_citation":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/action/citation_signature","submit_replication":"https://pith.science/pith/NPXG26NONTZMMBTILRZ3EY6KWU/action/replication_record"}},"created_at":"2026-07-05T00:39:10.069444+00:00","updated_at":"2026-07-05T00:39:10.069444+00:00"}